scholarly journals Research on Fault Feature Extraction Method Based on NOFRFs and Its Application in Rotor Faults

2019 ◽  
Vol 2019 ◽  
pp. 1-11
Author(s):  
Yang Liu ◽  
Yulai Zhao ◽  
Jintao Li ◽  
Fangquan Xi ◽  
Shuanghe Yu ◽  
...  
Keyword(s):  
Early Stage ◽  
Recognition Rate ◽  
High Order ◽  
Nonlinear Phenomena ◽  
Contribution Rate ◽  
Output Frequency ◽  
Nonlinear Characteristics ◽  
Feature Extraction Method ◽  
Rotor Faults ◽  
Fault Feature Extraction

Rub-impact between the rotating and static parts is a more common fault. The occurrence of faults is often accompanied by the generation of nonlinear phenomena. However, it is difficult to find out because the nonlinear characteristics are not obvious at the beginning of the fault. As a new frequency domain-based method, nonlinear output frequency response functions (NOFRFs) use the vibration response to extract the nonlinear characteristics of the system. This method has a better recognition rate for fault detection. Also, it has been applied in structural damages detection, but the high-order NOFRFs have the characteristics that the signals are weak and the features are difficult to extract. On this basis, the concept of the weighted contribution rate of the NOFRFs is proposed in this paper. The variable weighted coefficients with orders are used to amplify the influence of high-order NOFRFs on the nonlinearity of the system so as to extract its fault characteristics. The new index RI is proposed based on Clenshaw–Curtis quadrature formula to eliminate the effect of artificially selected weighted coefficients on sensitivity. Especially in the early stage of the fault, the new index varies greatly with the deepening of the fault. Both simulation and experimental results verify the validity and practicability of the new index. The new index has certain guiding significance in the detection of mechanical system faults.

Feature Extraction of Diesel Engine Wear Fault Based on Local Tangent Space Alignment

2013 ◽  
Vol 482 ◽  
pp. 179-182 ◽  
Author(s):  
Hai Bing Xiao ◽  
Xiao Peng Xie ◽  
Shou Qin Zhou ◽  
Heng Xing Xie
Keyword(s):  
Feature Extraction ◽  
Diesel Engine ◽  
Tangent Space ◽  
Recognition Rate ◽  
Classification Performance ◽  
Test Rig ◽  
Feature Extraction Method ◽  
Engine Wear ◽  
Fault Feature Extraction ◽  
Local Tangent

In view of diesel engine wear fault feature extraction, feature extraction of diesel engine wear fault based on Local Tangent Space Alignment (LTSA) was put forward. This paper analyzes LTSA algorithm which reveals the characteristics of manifold learning. Take diesel engine fault diagnosis test rig as example, vibration information was got through imitating different kinds of diesel engine wear fault. LTSA algorithm was applied for dimensionality reduction. LTSA algorithm’s classification performance was compared in accordance with recognition rate of multi-class SVM. The experimental results show that LTSA has high recognition rate and is a very effective feature extraction method for diesel engine wear fault.

scholarly journals Texture Feature Extraction Method for Ground Nephogram Based on Hilbert Spectrum of Bidimensional Empirical Mode Decomposition

2014 ◽  
Vol 31 (9) ◽  
pp. 1982-1994 ◽  
Author(s):  
Xiaoying Chen ◽  
Aiguo Song ◽  
Jianqing Li ◽  
Yimin Zhu ◽  
Xuejin Sun ◽  
...  
Keyword(s):  
Empirical Mode Decomposition ◽  
Recognition Rate ◽  
Texture Feature ◽  
Intrinsic Mode Functions ◽  
Hilbert Spectrum ◽  
Feature Extraction Method ◽  
Hilbert Huang Transform ◽  
Mode Decomposition ◽  
Marginal Spectrum ◽  
Bidimensional Empirical Mode Decomposition

Abstract It is important to recognize the type of cloud for automatic observation by ground nephoscope. Although cloud shapes are protean, cloud textures are relatively stable and contain rich information. In this paper, a novel method is presented to extract the nephogram feature from the Hilbert spectrum of cloud images using bidimensional empirical mode decomposition (BEMD). Cloud images are first decomposed into several intrinsic mode functions (IMFs) of textural features through BEMD. The IMFs are converted from two- to one-dimensional format, and then the Hilbert–Huang transform is performed to obtain the Hilbert spectrum and the Hilbert marginal spectrum. It is shown that the Hilbert spectrum and the Hilbert marginal spectrum of different types of cloud textural images can be divided into three different frequency bands. A recognition rate of 87.5%–96.97% is achieved through random cloud image testing using this algorithm, indicating the efficiency of the proposed method for cloud nephogram.

High Order Nonlinear Characteristics for Electromagnetically Induced Transparency Media

2014 ◽  
Vol 34 (6) ◽  
pp. 0627001
Author(s):  
杜英杰 Du Yingjie ◽  
杨战营 Yang Zhanying ◽  
白晋涛 Bai Jintao
Keyword(s):  
Electromagnetically Induced Transparency ◽  
High Order ◽  
Nonlinear Characteristics ◽  
Induced Transparency

scholarly journals Research on the Fault Feature Extraction Method of Rotor Systems Based on GAW-PSO

2020 ◽  
Vol 2020 ◽  
pp. 1-10 ◽  
Author(s):  
Feng Miao ◽  
Rongzhen Zhao ◽  
Xianli Wang
Keyword(s):  
Feature Extraction ◽  
Optimization Method ◽  
Population Diversity ◽  
Blind Separation ◽  
Feature Extraction Method ◽  
Rotor Systems ◽  
The Difference ◽  
Dynamic Hybrid ◽  
Fault Feature Extraction ◽  
Better Than

In order to solve the problem of blind separation of signals from dynamic hybrid rotor systems, this paper proposed an improved adaptive inertial weight particle swarm optimization method based on genetic mechanism. The method takes the negative entropy of separated signal as the objective function and adaptively adjusts the inertia weight according to the difference of particle fitness, thus reducing the number of invalid iterations. At the same time, genetic hybridization mechanism was introduced to increase population diversity and facilitate the processing of dynamic mixed signals. The orthogonal matrix is expressed as a parameterized form, which can reduce the complexity of the algorithm. The simulation results showed that the performance of the proposed method is better than that of the traditional method for blind separation of dynamic hybrid analog mechanical signals. It can separate the actual dynamic rotor system signals and achieve the purpose of fault feature extraction.

Sign in / Sign up

Export Citation Format

Share Document